Hugging Face's logo

khtsly
/
Mini-Coder-GGUF

Image-Text-to-Text
GGUF
English
Chinese
qwen3_5
unsloth
qwen
qwen3.5
reasoning
chain-of-thought
lora
luau
roblox
llama.cpp
vision-language-model
conversational
Model card Files
xet
 Community
khtsly commited on
Commit
5fb8754
·
verified ·
1 Parent(s): e0f87a9

Trained with Unsloth - config

Browse files
Files changed (1) hide show
  1. config.json +112 -0
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "torch_dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "model_name": "Qwen/Qwen3.5-9B",
8
+ "model_type": "qwen3_5",
9
+ "pad_token_id": 248044,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "attn_output_gate": true,
14
+ "bos_token_id": null,
15
+ "torch_dtype": "bfloat16",
16
+ "eos_token_id": 248044,
17
+ "full_attention_interval": 4,
18
+ "head_dim": 256,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 4096,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 12288,
23
+ "layer_types": [
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention"
56
+ ],
57
+ "linear_conv_kernel_dim": 4,
58
+ "linear_key_head_dim": 128,
59
+ "linear_num_key_heads": 16,
60
+ "linear_num_value_heads": 32,
61
+ "linear_value_head_dim": 128,
62
+ "mamba_ssm_dtype": "float32",
63
+ "max_position_embeddings": 262144,
64
+ "mlp_only_layers": [],
65
+ "model_type": "qwen3_5_text",
66
+ "mtp_num_hidden_layers": 1,
67
+ "mtp_use_dedicated_embeddings": false,
68
+ "num_attention_heads": 16,
69
+ "num_hidden_layers": 32,
70
+ "num_key_value_heads": 4,
71
+ "pad_token_id": null,
72
+ "partial_rotary_factor": 0.25,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_parameters": {
75
+ "mrope_interleaved": true,
76
+ "mrope_section": [
77
+ 11,
78
+ 11,
79
+ 10
80
+ ],
81
+ "partial_rotary_factor": 0.25,
82
+ "rope_theta": 10000000,
83
+ "rope_type": "default"
84
+ },
85
+ "tie_word_embeddings": false,
86
+ "use_cache": true,
87
+ "vocab_size": 248320
88
+ },
89
+ "tie_word_embeddings": false,
90
+ "unsloth_version": "2026.3.10",
91
+ "use_cache": false,
92
+ "video_token_id": 248057,
93
+ "vision_config": {
94
+ "deepstack_visual_indexes": [],
95
+ "depth": 27,
96
+ "torch_dtype": "bfloat16",
97
+ "hidden_act": "gelu_pytorch_tanh",
98
+ "hidden_size": 1152,
99
+ "in_channels": 3,
100
+ "initializer_range": 0.02,
101
+ "intermediate_size": 4304,
102
+ "model_type": "qwen3_5",
103
+ "num_heads": 16,
104
+ "num_position_embeddings": 2304,
105
+ "out_hidden_size": 4096,
106
+ "patch_size": 16,
107
+ "spatial_merge_size": 2,
108
+ "temporal_patch_size": 2
109
+ },
110
+ "vision_end_token_id": 248054,
111
+ "vision_start_token_id": 248053
112
+ }